Back to overview
CoSyne - Multi-Lingual Content Synchronisation with Wikis
248531- STREP

At a glance
ICT-2007.2.2 - Cognitive Systems, Interaction, Robotics
- Duration: 36 months
- Start date: 1 March 2010
- End date: 28 February 2013
-
Project officer: Philippe Gelin
- Website
- Video
- Poster
- Flyer
- Annual Report 2011
At a glance
ICT-2007.2.2 - Cognitive Systems, Interaction, Robotics
- Duration: 36 months
- Start date: 1 March 2010
- End date: 28 February 2013
- Project officer: Philippe Gelin
- Website
- Video
- Poster
- Flyer
- Annual Report 2011
The combination of dynamic user-generated content and multi-lingual aspects is particularly prominent in Wiki sites. Wikis have gained increased popularity over the last few years as a means of collaborative content creation as they allow users to set up and edit web pages directly. A growing number of organisations use Wikis as an efficient means to provide and maintain information across several sites.
Challenge
Currently, multi-lingual Wikis rely on users to manually translate different Wiki pages on the same subject. This is not only a time-consuming procedure but also the source of many inconsistencies, as users update the different language versions separately, and every update would require translators to compare the different language versions and synchronise the updates.
Goal
The overall aim of the CoSyne project is to automate the dynamic multi-lingual synchronisation process of Wikis.
Scientific Innovation
CoSyne will:
- achieve robust translation of noisier user-generated content between 6 core languages (consisting of 4 core languages and 2 languages with limited resources to demonstrate adaptability of the system);
- improve machine translation quality by segment-specific adaptive modelling;
- identify textual content overlap between segments of Wiki pages across languages to avoid redundant machine translation;
- identify the optimal insertion points for translated content to preserve coherence;
- analyse user edits to distinguish between factual content changes and corrections of machine translation output, and exploit the latter to improve machine translation performance in a self-learning manner.
The result
The components of CoSyne will be integrated through web services with the open-source MediaWiki platform, which is the most commonly used Wiki platform.
Impact
The three end-user partners of the consortium will deploy, integrate into their daily workflow, and evaluate the CoSyne system, which will give a clear direction towards the exploitability of the project's outcomes.
| Co-ordinator |
Contact Person: Name: Christof Monz Tel: +31 20 525 8676 Fax: +31 20 525 7490 E-mail: c.monz@uva.nl Organisation: University of Amsterdam |
| Participants |
|
This page is maintained by: Susan Fraser
